UAV-AdNet: Unsupervised Anomaly Detection using Deep Neural Networks for Aerial Surveillance

Ilker Bozcan, Erdal Kayacan

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

Anomaly detection is a key goal of autonomous surveillance systems that should be able to alert unusual observations. In this paper, we propose a holistic anomaly detection system using deep neural networks for surveillance of critical infrastructures (e.g., airports, harbors, warehouses) using an unmanned aerial vehicle (UAV). First, we present a heuristic method for the explicit representation of spatial layouts of objects in bird-view images. Then, we propose a deep neural network architecture for unsupervised anomaly detection (UAV-AdNet), which is trained on environment representations and GPS labels of bird-view images jointly. Unlike studies in the literature, we combine GPS and image data to predict abnormal observations. We evaluate our model against several baselines on our aerial surveillance dataset and show that it performs better in scene reconstruction and several anomaly detection tasks. The codes, trained models, dataset, and video will be available at https://bozcani.github.io/uavadnet.

OriginalsprogEngelsk
Titel2020 IEEE/RSJ International Conference on Intelligent Robots and Systems
Antal sider7
ForlagIEEE
Publikationsdatookt. 2020
Sider1158-1164
Artikelnummer9341790
ISBN (Elektronisk)9781728162126
DOI
StatusUdgivet - okt. 2020
Begivenhed2020 IEEE/RSJ International Conference on Intelligent Robots and Systems - Caesars Forum, Las Vegas, USA
Varighed: 25 okt. 202024 jan. 2021
https://www.iros2020.org/

Konference

Konference2020 IEEE/RSJ International Conference on Intelligent Robots and Systems
LokationCaesars Forum
Land/OmrådeUSA
ByLas Vegas
Periode25/10/202024/01/2021
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'UAV-AdNet: Unsupervised Anomaly Detection using Deep Neural Networks for Aerial Surveillance'. Sammen danner de et unikt fingeraftryk.

Citationsformater